Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_camel_biology

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
cc372b1
·
verified ·
1 Parent(s): 332f310

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +2 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23192a3de29ad2ef7a1929ce818abf1e2c246c3a501bc48c66497b54bc662d09
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d82203c2007e05139284f9da156fcdda0eb7f4768877fbe59510a90c0980c9e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a767360078bf92885cad3f7ef2b7edbf0eb580225f2667f7fb6624ad9a55a4fb
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f1120c01b55b3c85d6d5f6ef65774b8856b4cc98c48019f0b8668326d8bd55
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67999e446fa2dabceb561c781762a1fdd00709630d79b14cc1c27a5fb78f9ae1
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844327083dd2be940722af3702af4f7007eacec7047497652c5f1ddbdeeef68a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b5eaa9ced2ba83e6a710aa824a34a5a9f415ca693774642f627c8b25ac39c21
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e8583f83520b189ba1f8f9302c01f6f63e38acceda47490ea19e074308a683
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,5 @@
2
  {"current_steps": 10, "total_steps": 24, "loss": 1.0808, "learning_rate": 5e-06, "epoch": 1.2173913043478262, "percentage": 41.67, "elapsed_time": "0:06:26", "remaining_time": "0:09:01"}
3
  {"current_steps": 16, "total_steps": 24, "eval_loss": 0.9052095413208008, "epoch": 1.9130434782608696, "percentage": 66.67, "elapsed_time": "0:09:46", "remaining_time": "0:04:53"}
4
  {"current_steps": 20, "total_steps": 24, "loss": 0.9702, "learning_rate": 5e-06, "epoch": 2.4347826086956523, "percentage": 83.33, "elapsed_time": "0:12:51", "remaining_time": "0:02:34"}
 
 
 
2
  {"current_steps": 10, "total_steps": 24, "loss": 1.0808, "learning_rate": 5e-06, "epoch": 1.2173913043478262, "percentage": 41.67, "elapsed_time": "0:06:26", "remaining_time": "0:09:01"}
3
  {"current_steps": 16, "total_steps": 24, "eval_loss": 0.9052095413208008, "epoch": 1.9130434782608696, "percentage": 66.67, "elapsed_time": "0:09:46", "remaining_time": "0:04:53"}
4
  {"current_steps": 20, "total_steps": 24, "loss": 0.9702, "learning_rate": 5e-06, "epoch": 2.4347826086956523, "percentage": 83.33, "elapsed_time": "0:12:51", "remaining_time": "0:02:34"}
5
+ {"current_steps": 24, "total_steps": 24, "eval_loss": 0.8778269290924072, "epoch": 2.898550724637681, "percentage": 100.0, "elapsed_time": "0:16:01", "remaining_time": "0:00:00"}
6
+ {"current_steps": 24, "total_steps": 24, "epoch": 2.898550724637681, "percentage": 100.0, "elapsed_time": "0:16:58", "remaining_time": "0:00:00"}